Pycon Israel 2021

Testing stochastic AI models with hypothesis
05-02, 15:30–15:55 (Asia/Jerusalem), PyData Track 1

In this talk, I will cover shortly the theory of property-based testing and then jump into use cases and live examples to demonstrate the hypothesis library and how we used it to generate random examples of plausible edge cases of our AI model.


Over the years, testing has become one of the main focus areas in development teams, a good feature is a well tested one. In the field of AI this is many times a real struggle. Since eventually most advanced AI models are stochastic - we can’t manually define all their possible edge cases. This led us to use the hypothesis library which does a lot of that for you, while you can focus on defining the properties and specifications of your system.

In this talk, I will cover shortly the theory of property-based testing and then jump into use cases and live examples to demonstrate how we used the hypothesis library to generate random examples of plausible edge cases of our AI model.


Session language

English

Target audience

Developers, Data Scientists

Marina is a senior A.I. software architect at Aidoc, working on building scalable A.I. infrastructure for the research and development of cutting edge A.I. algorithms in the field of healthcare. She has 9 years of experience as a software engineer and software team leader, working both in corporate companies and startups.
She's passionate about finding the best architecture and solutions to software problems and mentoring others with her experience and knowledge.